Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or reasons for events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.77
     perſon
    -0.69
     Chriftian
    -0.65
     houſe
    -0.62
     anſ
    -0.60
     sánchez
    -0.60
     tranſ
    -0.60
     ſtill
    -0.59
     Jefus
    -0.58
     pleaſure
    -0.58
    POSITIVE LOGITS
     due
    1.42
     DUE
    1.29
     Due
    1.27
    due
    1.24
    Due
    1.22
    DUE
    1.16
     devido
    0.96
     debido
    0.83
     Aufgrund
    0.77
     owing
    0.77
    Act Density 0.218%

    No Known Activations